© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28285
    Prev
    Next
    INDEX
    Explanations

    confirming or confirming statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĻij
    -0.08
     kontra
    -0.08
    emus
    -0.08
    å±ħæĺĵ
    -0.07
     allegedly
    -0.07
    åı¯èĥ½ä¼ļ导èĩ´
    -0.07
    éľĢè¦ģèĢĥèĻij
    -0.07
    åı¯èĥ½å¯¼èĩ´
    -0.07
    estand
    -0.07
    æĮīçIJĨ
    -0.07
    POSITIVE LOGITS
    说æĺİ
    0.09
     confirming
    0.09
     confirms
    0.09
    确认åIJİ
    0.08
    确认
    0.08
    ìŀĦìĿĦ
    0.08
    æ¯ıæĹ¥ä¸Ģ
    0.08
     bestätigt
    0.07
    è¯ģå®ŀ
    0.07
    ç¡®å®ŀæĺ¯
    0.07
    Activations Density 0.010%

    No Known Activations